Accurate prediction of scoliotic curve progression is crucial for guiding treatment decisions in adolescent idiopathic scoliosis (AIS). Traditional methods of assessing the likelihood of AIS progression are limited by variability and rely on static measurements. This study developed and validated machine learning models for classifying progressive and non-progressive scoliotic curves based on gait analysis using wearable inertial sensors. Gait data from 38 AIS patients were collected using seven inertial measurement unit (IMU) sensors, and hip–knee (HK) cyclograms representing inter-joint coordination were generated. Various machine learning algorithms, including support vector machine (SVM), random forest (RF), and novel deep convolutional neural network (DCNN) models utilizing multi-plane HK cyclograms, were developed and evaluated using 10-fold cross-validation. The DCNN model incorporating multi-plane HK cyclograms and clinical factors achieved an accuracy of 92% in predicting curve progression, outperforming SVM (55% accuracy) and RF (52% accuracy) models using handcrafted gait features. Gradient-based class activation mapping revealed that the DCNN model focused on the swing phase of the gait cycle to make predictions. This study demonstrates the potential of deep learning techniques, and DCNNs in particular, in accurately classifying scoliotic curve progression using gait data from wearable IMU sensors.

Objective: To investigate longitudinal changes in plantar pressure examinations and plain radiographs and to assess the correlations between these two modalities in pediatric patients with flexible flatfoot (FFF).Methods: Pediatric patients diagnosed with FFF were analyzed in this retrospective cohort study. Medical records were reviewed to collect data on plain radiographs and plantar pressure examinations. Changes in radiographic angles and plantar pressure parameters were analyzed over a follow-up period exceeding 1 year. Statistical analyses included paired t-test, Wilcoxon signed rank test, and Spearman’s correlation analysis.Results: A total of 52 subjects was included in the plantar pressure analysis, with a mean age of 9.9 years at the first visit and a median follow-up duration of 52 months. The lateral tarso-first metatarsal angle decreased by 1.3° (p<0.001) and calcaneal inclination angle increased by 2.5° (p<0.001) in these patients. The percentage value of midfoot width (WMF) divided by forefoot width (WFF) decreased by an average of 9.8% p (p<0.001), and the maximal pressure on the medial midfoot (MMF) decreased by 1.6 N/cm2 (p<0.001). However, no correlations were found between plantar pressure and radiographic changes.Conclusion: During follow-up of patients with FFF, the maximal pressure on the MMF and the ratio of WMF to WFF decreased in successive plantar pressure examinations. Changes observed in plantar pressure and plain radiographs were not consistent, indicating that these two testing modalities can complement each other.